{
  "best_metric": 1.7429991960525513,
  "best_model_checkpoint": "./outputs/checkpoint-1100",
  "epoch": 0.8014571948998178,
  "eval_steps": 100,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.3152,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.160670518875122,
      "eval_runtime": 143.4488,
      "eval_samples_per_second": 43.737,
      "eval_steps_per_second": 5.472,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.1094,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.0639851093292236,
      "eval_runtime": 143.5664,
      "eval_samples_per_second": 43.701,
      "eval_steps_per_second": 5.468,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.0347,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.0028491020202637,
      "eval_runtime": 143.5409,
      "eval_samples_per_second": 43.709,
      "eval_steps_per_second": 5.469,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.9808,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 1.9539737701416016,
      "eval_runtime": 143.5859,
      "eval_samples_per_second": 43.695,
      "eval_steps_per_second": 5.467,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.9262,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 1.911293625831604,
      "eval_runtime": 143.5587,
      "eval_samples_per_second": 43.703,
      "eval_steps_per_second": 5.468,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.8974,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 1.8804633617401123,
      "eval_runtime": 143.5407,
      "eval_samples_per_second": 43.709,
      "eval_steps_per_second": 5.469,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.8572,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.8469738960266113,
      "eval_runtime": 143.4729,
      "eval_samples_per_second": 43.73,
      "eval_steps_per_second": 5.471,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.8337,
      "step": 800
    },
    {
      "epoch": 0.58,
      "eval_loss": 1.8184312582015991,
      "eval_runtime": 143.5016,
      "eval_samples_per_second": 43.721,
      "eval_steps_per_second": 5.47,
      "step": 800
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.7964,
      "step": 900
    },
    {
      "epoch": 0.66,
      "eval_loss": 1.7926479578018188,
      "eval_runtime": 143.5332,
      "eval_samples_per_second": 43.711,
      "eval_steps_per_second": 5.469,
      "step": 900
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.7803,
      "step": 1000
    },
    {
      "epoch": 0.73,
      "eval_loss": 1.7669757604599,
      "eval_runtime": 143.5614,
      "eval_samples_per_second": 43.703,
      "eval_steps_per_second": 5.468,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.76,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.7429991960525513,
      "eval_runtime": 143.4985,
      "eval_samples_per_second": 43.722,
      "eval_steps_per_second": 5.47,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 6.550064066907341e+16,
  "trial_name": null,
  "trial_params": null
}